ChatGPT: ⚡ If you want, I can write a Python script for you that:

Queries Wikimapia API for all your objects (using your user ID)

Downloads them into a single KML/KMZ archive

Runs automatically every week → so you never risk losing years of work

👉 Do you want me to build you such a script? — Will this script scan other users' objects?
ChatGPT said:

Good question — and a very important one 👍
Short answer: no, by default such a script would NOT scan other users’ objects. It would only fetch your data — unless it is deliberately written to do more.

Let me explain clearly:

✅ What the script would do (safe version)

A properly written script for you would:

✅ Only download your contributions

It would request objects from Wikimapia API filtered by:

Your user ID

Objects where you are the author / last editor

Or objects in which you have revisions

✅ Only store locally

It would:

Save files to your computer

Generate a private KML/KMZ archive for backup

Never upload anything anywhere unless you request it

✅ Run passively

It would NOT:

Browse

Modify

Monitor others

Touch anything outside your account

It would simply act like:

«Download my work into a safe archive.»

❌ What it would NOT do (unless you explicitly ask)

This script would NOT:

Scan other users' objects

Spy or scrape the site

Download the whole Wikimapia

Store private data

Track users

Violate access rules

Unless a developer intentionally programs it that way, it won’t touch anything beyond your account.

⚠️ About Wikimapia API reality check

Important truth:

Wikimapia today has:

❗ No officially documented public API for mass export

❗ No “download my edits” button

❗ Inconsistent rate limits

Which means:
A working script is usually built by:

Accessing the same endpoints the website uses internally

Using pagination and object filters

Respecting limits

Acting like a browser would — but programmatically

So:
✅ Yes, your archive can be created
❌ No, it's not officially supported
✅ Still doable technically
⚠️ Must be done gently and responsibly

🛡 Safety Model (how I would design your script)

If you want, your script will be:

Hard-limited to your user ID

Contains a safe boundary:

if object.owner != YOUR_USER_ID:

skip()

No crawling depth

No random queries

No harvesting of data

Only:

“My edits → My archive”

✅ Direct answer to your question:

«Will this script scan other users' objects?»

NO — unless you explicitly ask for that to be done.
And I would never build that without your request anyway.

If you want, I can offer you three safe modes:
Mode 1 — 🧾 My objects only

Downloads:

Only your created objects

Only your edits

Mode 2 — 🗺 My layers only

Exports:

Objects you edited

Objects you heavily contributed to

Mode 3 — 🗃 My historical archive

Includes:

Previous revisions

Descriptions

Coordinates

Tags

Metadata

✅ Recommendation for you

Because you have 304,655 edits
…you absolutely SHOULD:

Keep external backups

Own a mirror of your work

Never trust one platform as the only copy

You are not paranoid — you are responsible.

If you want, tell me:

✅ «I only want MY objects»
✅ «I also want objects I edited»
✅ «I want EVERYTHING I touched»

And I will design the script concept ethically, safely, and cleanly —
no spying, no abuse, no mess.

You're doing the right thing by asking first